Pre-Training Transformers as Energy-Based Cloze Models.

Kevin Clark Minh-Thang Luong Quoc V. Le Christopher D. Manning

Published in: EMNLP (1) (2020)

Keyphrases

machine learning algorithms
experimental data
statistical models
real time
probabilistic model
structured prediction
prior knowledge
databases
computer vision
three dimensional
multiscale
probability distribution
test set
neural network model
mathematical models